UoB at SemEval-2021 Task 5: Extending Pre-Trained Language Models to Include Task and Domain-Specific Information for Toxic Span Prediction
| Autor: | Erik Yan, Harish Tayyar Madabushi |
|---|---|
| Jazyk: | angličtina |
| Rok vydání: | 2021 |
| Předmět: |
FOS: Computer and information sciences
Conditional random field Computer Science - Computation and Language Computer science business.industry Specific-information Machine learning computer.software_genre Security token SemEval Task (project management) Domain (software engineering) Language model Artificial intelligence business Computation and Language (cs.CL) Implementation computer |
| Zdroj: | SemEval@ACL/IJCNLP |
| Popis: | Toxicity is pervasive in social media and poses a major threat to the health of online communities. The recent introduction of pre-trained language models, which have achieved state-of-the-art results in many NLP tasks, has transformed the way in which we approach natural language processing. However, the inherent nature of pre-training means that they are unlikely to capture task-specific statistical information or learn domain-specific knowledge. Additionally, most implementations of these models typically do not employ conditional random fields, a method for simultaneous token classification. We show that these modifications can improve model performance on the Toxic Spans Detection task at SemEval-2021 to achieve a score within 4 percentage points of the top performing team. Published in Proceedings of the 15th International Workshop on Semantic Evaluation (SemEval-2021); Code available at: https://github.com/erikdyan/toxic_span_detection |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|